U.S. patent application number 14/739079 was filed with the patent office on 2016-12-15 for teaching aid using predicted patterns in spelling errors.
The applicant listed for this patent is International Business Machines Corporation. Invention is credited to Lakshminarayanan Krishnamurthy, Niyati Parameswaran, Edward E. Seabolt, Paul T. Wright.
Application Number | 20160364992 14/739079 |
Document ID | / |
Family ID | 57517106 |
Filed Date | 2016-12-15 |
United States Patent
Application |
20160364992 |
Kind Code |
A1 |
Krishnamurthy; Lakshminarayanan ;
et al. |
December 15, 2016 |
TEACHING AID USING PREDICTED PATTERNS IN SPELLING ERRORS
Abstract
Teaching aid for improving the spelling competency of a student.
The framework provides differentiated instruction and tailors
interventions specific to the needs of the student by taking into
account relative performance of peers and the root cause of an
identified spelling error.
Inventors: |
Krishnamurthy;
Lakshminarayanan; (Round Rock, TX) ; Parameswaran;
Niyati; (Austin, TX) ; Seabolt; Edward E.;
(Round Rock, TX) ; Wright; Paul T.; (Austin,
TX) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
International Business Machines Corporation |
Armonk |
NY |
US |
|
|
Family ID: |
57517106 |
Appl. No.: |
14/739079 |
Filed: |
June 15, 2015 |
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
G09B 5/06 20130101; G09B
19/00 20130101 |
International
Class: |
G09B 5/00 20060101
G09B005/00; G09B 19/00 20060101 G09B019/00 |
Claims
1. A method comprising: assigning a first set of root causes to a
first error type of a set of error types; monitoring a spelling
event of a user for a misspelled word based, at least in part, on a
set of target words; determining that the misspelled word is a
misspelling of a target word of a set of target words according to
the first error type; generating a set of training words based, at
least in part, on a characteristic of the target word; and
selecting from the set of training words, a set of focus words
based, at least in part, on the first set of root causes; wherein:
at least the determining, generating, and selecting steps are
performed by computer software running on computer hardware.
2. The method of claim 1, wherein the step of generating a set of
training words is further based on a characteristic of the
user.
3. The method of claim 1, wherein the spelling event is a spelling
by the user of a single word while using a word processor.
4. The method of claim 3, wherein the monitoring step is performed
by the word processor.
5. The method of claim 1, further comprising: deriving the set of
error types from a comparison of a correct letter placement with an
incorrect letter placement of the misspelled word.
6. The method of claim 5, wherein the first error type is where the
comparison of the correct letter placement with the incorrect
letter placement of the misspelled word is one of an insertion, a
swap, or a combination of the two.
7. The method of claim 1, further comprising: collecting the set of
target words from documents found on the internet.
8. The method of claim 1, further comprising: creating a spelling
challenge activity that incorporates at least some of the focus
words from the set of focus words.
9. A computer program product comprising a computer readable
storage medium having stored thereon: first program instructions
programmed to assign a first set of root causes to a first error
type of a set of error types; second program instructions
programmed to monitor a spelling event of a user for a misspelled
word based, at least in part, on a set of target words; third
program instructions programmed to determine that the misspelled
word is a misspelling of a target word of a set of target words
according to the first error type; fourth program instructions
programmed to generate a set of training words based, at least in
part, on a characteristic of the target word; and fifth program
instructions programmed to select from the set of training words, a
set of focus words based, at least in part, on the first set of
root causes.
10. The computer program product of claim 9, wherein generating a
set of training words is further based on a characteristic of the
user.
11. The computer program product of claim 9, wherein the spelling
event is a spelling by the user of a single word while using a word
processor.
12. The computer program product of claim 9, further comprising:
sixth program instructions programmed to derive the set of error
types from a comparison of a correct letter placement with an
incorrect letter placement of the misspelled word.
13. The computer program product of claim 9, further comprising:
sixth program instructions programmed to create a spelling
challenge activity that incorporates at least some of the focus
words from the set of focus words.
14. A computer system comprising: a processor(s) set; and a
computer readable storage medium; wherein: the processor set is
structured, located, connected, and/or programmed to run program
instructions stored on the computer readable storage medium; and
the program instructions include: first program instructions
programmed to assign a first set of root causes to a first error
type of a set of error types; second program instructions
programmed to monitor a spelling event of a user for a misspelled
word based, at least in part, on a set of target words; third
program instructions programmed to determine that the misspelled
word is a misspelling of a target word of a set of target words
according to the first error type; fourth program instructions
programmed to generate a set of training words based, at least in
part, on a characteristic of the target word; and fifth program
instructions programmed to select from the set of training words, a
set of focus words based, at least in part, on the first set of
root causes.
15. The computer system of claim 14, wherein generating a set of
training words is further based on a characteristic of the
user.
16. The computer system of claim 14, wherein the spelling event is
a spelling by the user of a single word while using a word
processor.
17. The computer system of claim 14, further comprising: sixth
program instructions programmed to derive the set of error types
from a comparison of a correct letter placement with an incorrect
letter placement of the misspelled word.
18. The computer system of claim 14, further comprising: sixth
program instructions programmed to create a spelling challenge
activity that incorporates at least some of the focus words from
the set of focus words.
Description
BACKGROUND
[0001] The present invention relates generally to the field of
analytics, and more particularly to teaching aids.
[0002] Spelling is one of the fundamental sub-skills of effective
written communication. The acquisition of spelling rules is a
complex developmental process. People commonly tend to make errors
when writing. Spelling errors, as discussed herein, are organized
according the following categories: (i) errors stemming from
incorrect typography; (ii) errors originating from poor language or
deficient literacy; and (iii) errors arising due to cases of
learning disabilities like dyslexia or dysgraphia.
[0003] Word processors play a significant role in handling most of
the spelling errors caused by the three categories listed above.
Word processors support persons while they write, for example,
emails, instant messages, and even blogs. Standard features of many
state-of-the-art word processors include spelling and grammar
checks, built-in thesaurus capability, and automatic text
correction. Word processors are indispensable tools that make
spelling corrections when using a computer a trivial task.
[0004] Conventionally, spelling software programs, also referred to
as "spellers," either correct a misspelled word or generate
potential suggestions for the misspelled word by testing the
written words against a dictionary of known words. More advanced
spellers use phonetic spell checking and produce a list of
candidate words that may have different spellings, but are homonyms
to the misspelled word. There is a large amount of literature that
focuses on improving the accuracy and the capabilities of automated
spell checkers.
SUMMARY
[0005] In one aspect of the present invention, a method, a computer
program product, and a system includes: assigning a first set of
root causes to a first error type of a set of error types,
monitoring a spelling event of a user for a misspelled word based,
at least in part, on a set of target words, determining that the
misspelled word is a misspelling of a target word of a set of
target words according to the first error type, generating a set of
training words based, at least in part, on a characteristic of the
target word, and selecting from the set of training words, a set of
focus words based, at least in part, on the first set of root
causes.
BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS
[0006] FIG. 1 is a schematic view of a first embodiment of a system
according to the present invention;
[0007] FIG. 2 is a flowchart showing a method performed, at least
in part, by the first embodiment system;
[0008] FIG. 3 is a schematic view of a machine logic (for example,
software) portion of the first embodiment system;
[0009] FIG. 4 is a diagram showing a diagnostic framework helpful
in understanding some embodiments of the present invention; and
[0010] FIG. 5 is a diagram showing example word analysis according
to some embodiments of the present invention.
DETAILED DESCRIPTION
[0011] Teaching aid for improving the spelling competency of a
student. The framework provides differentiated instruction and
tailors interventions specific to the needs of the student by
taking into account relative performance of peers and the root
cause of an identified spelling error. The present invention may be
a system, a method, and/or a computer program product. The computer
program product may include a computer readable storage medium (or
media) having computer readable program instructions thereon for
causing a processor to carry out aspects of the present
invention.
[0012] The computer readable storage medium can be a tangible
device that can retain and store instructions for use by an
instruction execution device. The computer readable storage medium
may be, for example, but is not limited to, an electronic storage
device, a magnetic storage device, an optical storage device, an
electromagnetic storage device, a semiconductor storage device, or
any suitable combination of the foregoing. A non-exhaustive list of
more specific examples of the computer readable storage medium
includes the following: a portable computer diskette, a hard disk,
a random access memory (RAM), a read-only memory (ROM), an erasable
programmable read-only memory (EPROM or Flash memory), a static
random access memory (SRAM), a portable compact disc read-only
memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a
floppy disk, a mechanically encoded device such as punch-cards or
raised structures in a groove having instructions recorded thereon,
and any suitable combination of the foregoing. A computer readable
storage medium, as used herein, is not to be construed as being
transitory signals per se, such as radio waves or other freely
propagating electromagnetic waves, electromagnetic waves
propagating through a waveguide or other transmission media (e.g.,
light pulses passing through a fiber-optic cable), or electrical
signals transmitted through a wire.
[0013] Computer readable program instructions described herein can
be downloaded to respective computing/processing devices from a
computer readable storage medium, or to an external computer or
external storage device via a network, for example, the Internet, a
local area network, a wide area network, and/or a wireless network.
The network may comprise copper transmission cables, optical
transmission fibers, wireless transmission, routers, firewalls,
switches, gateway computers, and/or edge servers. A network adapter
card or network interface in each computing/processing device
receives computer readable program instructions from the network,
and forwards the computer readable program instructions for storage
in a computer readable storage medium within the respective
computing/processing device.
[0014] Computer readable program instructions for carrying out
operations of the present invention may be assembler instructions,
instruction-set-architecture (ISA) instructions, machine
instructions, machine dependent instructions, microcode, firmware
instructions, state-setting data, or either source code or object
code written in any combination of one or more programming
languages, including an object oriented programming language such
as Smalltalk, C++ or the like, and conventional procedural
programming languages, such as the "C" programming language or
similar programming languages. The computer readable program
instructions may execute entirely on the user's computer, partly on
the user's computer, as a stand-alone software package, partly on
the user's computer and partly on a remote computer, or entirely on
the remote computer or server. In the latter scenario, the remote
computer may be connected to the user's computer through any type
of network, including a local area network (LAN) or a wide area
network (WAN), or the connection may be made to an external
computer (for example, through the Internet using an Internet
Service Provider). In some embodiments, electronic circuitry
including, for example, programmable logic circuitry,
field-programmable gate arrays (FPGA), or programmable logic arrays
(PLA) may execute the computer readable program instructions by
utilizing state information of the computer readable program
instructions to personalize the electronic circuitry, in order to
perform aspects of the present invention.
[0015] Aspects of the present invention are described herein with
reference to flowchart illustrations and/or block diagrams of
methods, apparatus (systems), and computer program products
according to embodiments of the invention. It will be understood
that each block of the flowchart illustrations and/or block
diagrams, and combinations of blocks in the flowchart illustrations
and/or block diagrams, can be implemented by computer readable
program instructions.
[0016] These computer readable program instructions may be provided
to a processor of a general purpose computer, special purpose
computer, or other programmable data processing apparatus to
produce a machine, such that the instructions, which execute via
the processor of the computer or other programmable data processing
apparatus, create means for implementing the functions/acts
specified in the flowchart and/or block diagram block or blocks.
These computer readable program instructions may also be stored in
a computer readable storage medium that can direct a computer, a
programmable data processing apparatus, and/or other devices to
function in a particular manner, such that the computer readable
storage medium having instructions stored therein comprises an
article of manufacture, including instructions which implement
aspects of the function/act specified in the flowchart and/or block
diagram block or blocks.
[0017] The computer readable program instructions may also be
loaded onto a computer, other programmable data processing
apparatus, or other device to cause a series of operational steps
to be performed on the computer, other programmable apparatus, or
other device to produce a computer implemented process, such that
the instructions which execute on the computer, other programmable
apparatus, or other device implement the functions/acts specified
in the flowchart and/or block diagram block or blocks.
[0018] The flowchart and block diagrams in the Figures illustrate
the architecture, functionality, and operation of possible
implementations of systems, methods, and computer program products
according to various embodiments of the present invention. In this
regard, each block in the flowchart or block diagrams may represent
a module, segment, or portion of instructions, which comprises one
or more executable instructions for implementing the specified
logical function(s). In some alternative implementations, the
functions noted in the block may occur out of the order noted in
the Figures. For example, two blocks shown in succession may, in
fact, be executed substantially concurrently, or the blocks may
sometimes be executed in the reverse order, depending upon the
functionality involved. It will also be noted that each block of
the block diagrams and/or flowchart illustration, and combinations
of blocks in the block diagrams and/or flowchart illustration, can
be implemented by special purpose hardware-based systems that
perform the specified functions, or acts, or carry out combinations
of special purpose hardware and computer instructions.
[0019] The present invention will now be described in detail with
reference to the Figures. FIG. 1 is a functional block diagram
illustrating various portions of networked computers system 100, in
accordance with one embodiment of the present invention, including:
training sub-system 102; client sub-systems 104, 106, 108, 110,
112; communication network 114; training computer 200;
communication unit 202; processor set 204; input/output (I/O)
interface set 206; memory device 208; persistent storage device
210; display device 212; external device set 214; random access
memory (RAM) devices 230; cache memory device 232; and spelling
program 300.
[0020] Sub-system 102 is, in many respects, representative of the
various computer sub-system(s) in the present invention.
Accordingly, several portions of sub-system 102 will now be
discussed in the following paragraphs.
[0021] Sub-system 102 may be a laptop computer, tablet computer,
netbook computer, personal computer (PC), a desktop computer, a
personal digital assistant (PDA), a smart phone, or any
programmable electronic device capable of communicating with the
client sub-systems via network 114. Program 300 is a collection of
machine readable instructions and/or data that is used to create,
manage, and control certain software functions that will be
discussed in detail below.
[0022] Sub-system 102 is capable of communicating with other
computer sub-systems via network 114. Network 114 can be, for
example, a local area network (LAN), a wide area network (WAN) such
as the Internet, or a combination of the two, and can include
wired, wireless, or fiber optic connections. In general, network
114 can be any combination of connections and protocols that will
support communications between server and client sub-systems.
[0023] Sub-system 102 is shown as a block diagram with many double
arrows. These double arrows (no separate reference numerals)
represent a communications fabric, which provides communications
between various components of sub-system 102. This communications
fabric can be implemented with any architecture designed for
passing data and/or control information between processors (such as
microprocessors, communications and network processors, etc.),
system memory, peripheral devices, and any other hardware component
within a system. For example, the communications fabric can be
implemented, at least in part, with one or more buses.
[0024] Memory 208 and persistent storage 210 are computer readable
storage media. In general, memory 208 can include any suitable
volatile or non-volatile computer readable storage media. It is
further noted that, now and/or in the near future: (i) external
device(s) 214 may be able to supply, some or all, memory for
sub-system 102; and/or (ii) devices external to sub-system 102 may
be able to provide memory for sub-system 102.
[0025] Program 300 is stored in persistent storage 210 for access
and/or execution by one or more of the respective computer
processors 204, usually through one or more memories of memory 208.
Persistent storage 210: (i) is at least more persistent than a
signal in transit; (ii) stores the program (including its soft
logic and/or data), on a tangible medium (such as magnetic or
optical domains); and (iii) is substantially less persistent than
permanent storage. Alternatively, data storage may be more
persistent and/or permanent than the type of storage provided by
persistent storage 210.
[0026] Program 300 may include both machine readable and
performable instructions, and/or substantive data (that is, the
type of data stored in a database). In this particular embodiment,
persistent storage 210 includes a magnetic hard disk drive. To name
some possible variations, persistent storage 210 may include a
solid state hard drive, a semiconductor storage device, read-only
memory (ROM), erasable programmable read-only memory (EPROM), flash
memory, or any other computer readable storage media that is
capable of storing program instructions or digital information.
[0027] The media used by persistent storage 210 may also be
removable. For example, a removable hard drive may be used for
persistent storage 210. Other examples include optical and magnetic
disks, thumb drives, and smart cards that are inserted into a drive
for transfer onto another computer readable storage medium that is
also part of persistent storage 210.
[0028] Communications unit 202, in these examples, provides for
communications with other data processing systems or devices
external to sub-system 102. In these examples, communications unit
202 includes one or more network interface cards. Communications
unit 202 may provide communications through the use of either, or
both, physical and wireless communications links. Any software
modules discussed herein may be downloaded to a persistent storage
device (such as persistent storage device 210) through a
communications unit (such as communications unit 202).
[0029] I/O interface set 206 allows for input and output of data
with other devices that may be connected locally in data
communication with computer 200. For example, I/O interface set 206
provides a connection to external device set 214. External device
set 214 will typically include devices such as a keyboard, keypad,
a touch screen, and/or some other suitable input device. External
device set 214 can also include portable computer readable storage
media such as, for example, thumb drives, portable optical or
magnetic disks, and memory cards. Software and data used to
practice embodiments of the present invention, for example, program
300, can be stored on such portable computer readable storage
media. In these embodiments the relevant software may (or may not)
be loaded, in whole or in part, onto persistent storage device 210
via I/O interface set 206. I/O interface set 206 also connects in
data communication with display device 212.
[0030] Display device 212 provides a mechanism to display data to a
user and may be, for example, a computer monitor or a smart phone
display screen.
[0031] The programs described herein are identified based upon the
application for which they are implemented in a specific embodiment
of the present invention. However, it should be appreciated that
any particular program nomenclature herein is used merely for
convenience, and thus the present invention should not be limited
to use solely in any specific application identified and/or implied
by such nomenclature.
[0032] Spelling support program 300 operates to both extrapolate
the conventional usage of a spell checker and to tailor
interventions that serve to improve the spelling competency of the
user in a specific and thorough way. Tailored interventions
executed through a diagnostic framework can be integrated as a
cognitive application fueled by cognitive computing technology in
fields such as education to work through the root cause(s) of
spelling errors to recommend actions. In some embodiments, the root
cause analysis and corresponding actions are determined in light of
spelling error categories, such as those provided in the Background
Section of this Specification.
[0033] Some embodiments of the present invention recognize the
following facts, potential problems and/or potential areas for
improvement with respect to the current state-of-the-art: (i)
conventional spelling software programs lack the ability to
determine the cause of a spelling error; (ii) conventional spelling
software programs use a binary classification scheme for spelling
correction; and/or (iii) it is prudent to exploit the fact that
every spelling error in English can be derived only on the basis of
certain operations on the letter(s) that form a given word.
[0034] Some embodiments of the present invention could be utilized
to effectively train students to correctly spell words in languages
other than English.
[0035] It should be noted that some embodiments of the present
invention apply to a language instruction guide for persons
learning English as a non-native language. For example, writing
samples from these persons are used to gauge the user's progress
with acquiring proficiency in English. Accordingly, a set of words
is generated based on the misspellings identified in the writing
sample to better focus assistance to the user's specific language
proficiency.
[0036] Every spelling error in English can be caused by operations
on the letter(s) that form a given word. The operations are
insertion(s), deletion(s), swap(s), and/or replacement(s). The
Damerau-Levenshtein distance is a string metric computed by
counting the minimum number of operations needed to transform a
first string into a second string. For example, the target word
"slow" may be incorrectly spelled as "slo" in a deletion operation,
where the letter "w" is deleted. The target word "camel" may be
incorrectly spelled as "cammel" in an insertion operation of the
letter "m." The target word "ginger" may be incorrectly spelled as
"jinger" in a replacement operation of the letter "g" with the
letter "j." The target word "friend" may be incorrectly spelled as
"freind" in a swap operation of the letters "I" and "e." The target
word "talk" may be incorrectly spelled as "tok" where multiple
operations are involved.
[0037] The Demerau-Levenshtein distance between two strings a and b
is given by the following formula:
d a , b ( a , b ) , where : ##EQU00001## d a , b ( i , j ) = { max
( i , j ) if min ( i , j ) - 0 , min { d a , b ( i - 1 , j ) + 1 d
a , b ( i , j - 1 ) + 1 d a , b ( i - 1 , j - 1 ) + 1 ( a i .noteq.
b j ) d a , b ( i - 2 , j - 2 ) + 1 if i , j > 1 and a i = b j -
1 and a i - 1 = b j , min { d a , b ( i - 1 , j ) + 1 d a , b ( i -
1 , j ) + 1 d a , b ( i - 1 , j - 1 ) + 1 ( a i .noteq. b j )
otherwise , ##EQU00001.2##
where 1.sub.(a.sub.i.sub..noteq.b.sub.j.sub.) is the indicator
function equal to 0 when a.sub.i=b.sub.j and equal to 1
otherwise.
[0038] Each recursive call matches one of the cases covered by the
Damerau-Levenshtein distance: [0039] d.sub.a,b(i-1,j)+1 corresponds
to a deletion (from a to b); [0040] d.sub.a,b(i,j-1)+1 corresponds
to an insertion (from a to b); [0041] d.sub.a,b(i-1,
j-1)+1.sub.(a.sub.i.sub..noteq.b.sub.j.sub.) corresponds to a match
or mismatch, depending on whether the respective symbols are the
same; and [0042] d.sub.a,b(i-2, j-2)+1 corresponds to a
transposition between two successive symbols.
[0043] FIG. 2 shows flowchart 250 depicting a first method
according to the present invention. FIG. 3 shows program 300 for
performing at least some of the method steps of flowchart 250. This
method and associated software will now be discussed, over the
course of the following paragraphs, with extensive reference to
FIG. 2 (for the method step blocks) and FIG. 3 (for the software
blocks).
[0044] Processing begins at step S255, where word list module "mod"
355 receives a target word list. In this example, there is a set of
target words for students to learn during a period of training.
These words are pre-determined according to a selected course
curriculum. One of the words is "sitting." Alternatively, the word
list is a collection of words obtained from selected websites.
Alternatively, the word list represents words used in a particular
set of documents stored in a database. Further discussion and more
details regarding sources from which the word list is prepared is
found below, particularly with respect to FIG. 4.
[0045] Processing proceeds to step S260, where monitor mod 360,
monitors spelling events of a user to identify a misspelled word in
the word list received in step S255. The term spelling events is
used broadly herein to include a variety of spelled word inputs
that may be generated by a user while demonstrating proficiency in
spelling. In this example, the spelling event occurs as the user
enters words into a conventional word processor for a homework
assignment to write about a selected topic. Accordingly, a spelling
event occurs each time a word is written. In that way, monitoring
occurs during the writing process in a manner that may be referred
to as in real-time. Alternatively, the monitor mod reviews a
completed written document, where the document is a single spelling
event.
[0046] Continuing with the example, monitor mod 360 detects a
misspelled word arising from the spelling event while monitoring a
spelling event. In this example, the monitor mod detects that the
word "sitting" is misspelled.
[0047] Processing proceeds to step S265, where error mod 365
determines a type of misspelling error associated with the
misspelled word. Some types of misspelling errors are discussed
below. In this example, error types are identified by comparing a
correctly spelled word with the misspelled word. Accordingly the
error types are relative to the correct spelling. For example,
misspelling error types include: (i) deletion; (ii) insertion;
(iii) replacement; and/or (iv) swapping. In this example, the word
"sitting" is spelled "siting." It can be seen that this misspelling
error type reflects the deletion-type of misspelling in that a
letter "T" is missing from the misspelled word. As discussed
further below, there are several root causes for spelling errors
including: (i) dyslexia; (ii) dysgraphia; (iii) rote visual; (iv)
memory; (v) semi-phonetic; (vi) word morphology; (vii) typography;
(viii) language skill; (ix) literacy; and/or (x) homonym. These
root causes are associated with one or more of the above-listed
misspelling error types.
[0048] Processing proceeds to step S270, where training mod 370
generates a set of training words based on the type of misspelling
error and/or characteristics of the misspelled word. In this
example, training words are identified from within the target word
list. Alternatively, training words are extracted from websites
and/or from a set of selected documents in a database. As described
in detail with reference to FIG. 5 below, word characteristics
include: (i) length; (ii) school grade level; (iii) structure; (iv)
context; and/or (v) syllables. Continuing with this example, the
set of training words generated for the word "sitting" are sorting,
hitting, setting, standing, bending, and running.
[0049] Additionally, the selection of the set of training words, in
some embodiments of the present invention, is for the purpose of
determining a root cause of the misspelled word. That is, the type
of misspelling error and/or characteristics of the misspelled word
are used to indicate which of the root causes to focus on and/or
which of the root causes to dismiss from consideration. The
selection of a word having particular characteristics may be made
in view of which root causes are being considered. For example, if
the root cause of poor language skills or deficient literacy is
being considered, the set of training words will focus, at least in
part, on word characteristics such as context and/or structure.
[0050] Alternatively, training words are selected in accordance
with the school grade level, or development stage, of a child
during the language acquisition process. The type(s) of errors in
the child's misspellings with respect to the training words are
analyzed for use in generating future test words. The future test
words tend to result in similar types of errors as the one(s) made
by the child during earlier training. In some embodiments of the
present invention, the test words are rendered in accordance with
the grade level, development stage, and/or level of language
proficiency of the child.
[0051] Processing proceeds to step S275, where challenge mod 375
creates a spelling challenge activity based on the set of training
words. Some embodiments of the present invention create a story
that includes some or all of the training words. In that way, the
story may be read aloud to the user, who writes down what is said.
The story telling approach provides for a rich context clue
environment. Alternatively, the training words are simply generated
in a list that is provided to an instructor, who provides each word
to the user as a spelling test. Further, some embodiments of the
present invention monitor the writing activity or spelling exam
while it is being performed as a set of spelling events for
processing according to step S260 and S265.
[0052] Further embodiments of the present invention are discussed
in the paragraphs that follow and later with reference to FIGS. 4
and 5.
[0053] Some embodiments of the present invention build upon a
conventional spell checker to use the flagged misspellings and
suggested corrections to align a particular child's misspelled
characters with the corresponding letters in the correctly spelled
target word, thereby tracking the type of error that a user made
when spelling the target word as opposed to just flagging it as
incorrect on the basis of a rigid binary classification scheme.
[0054] Some embodiments of the present invention are deployed
having a series of hash functions that successfully map all
potential misspellings of a target word to the correctly spelled
target word through a Bloom filter implementation. The principle is
premised on a reverse lookup that not only elucidates the cause of
the spelling error (as illustrated earlier), but also predicts a
sense of "commonality in the misspellings" by correlating the
misspellings the child has a tendency to make (Domain 1) to the
misspellings that similarly-situated children, for example, a
similar age-group, make generated by associating probabilistic
percentages for every word (Domain 2).
[0055] The overlap between Domains 1 and 2 is computed through a
TF-IDF (term frequency-inverse document frequency) score. A
relatively large overlap between Domains 1 and 2 serves to support
the commonality of the child's misspelling. However, relatively
little overlap, or a predetermined level of distinction, between
the two domains indicates an uncommon pattern in misspellings with
respect to the similarly-situated children. This condition is of
particular interest to a "spelling buddy" embodiment that captures
the individuality in misspellings and feeds in a value into the
Bloom filter derived from the parallel drawn against the two
domains.
[0056] An example Bloom filter k-mer counting algorithm
follows:
TABLE-US-00001 B .rarw. empty Bloom filter of size m T .rarw. hash
table for all reads .delta. do for all k-mers in .delta. do
.sub.rep .rarw. min( , revcomp( ))// .sub.rep is the canonical
k-mer for if .sub.rep .di-elect cons. B then if .sub.rep T then T[
.sub.rep] .rarw. 0 else add .sub.rep to B for all reads .delta. do
for all k-mers in .delta. do .sub.rep .rarw. min( , revcomp( )) if
.sub.rep .di-elect cons. T then T[ .sub.rep] .rarw. T[ .sub.rep] +
1 for all .di-elect cons. T do if T[ ] = 1 then remove from T
[0057] Through the execution of this embodiment, the type of
spelling errors are highlighted, such as a repeated transposition
pattern, incorrect single/double letter usage, phonetic
misspelling, or an erroneous intra-word pattern, but the
orthography and morphology are correlated back through a K-means
clustering algorithm that groups words of higher similarity (lower
edit distance) by using word length, number of syllables, word
structure (pre-fix, suffix), and word context as primary features.
The feedback garnered from the assessment described above
(especially in the case of too many uncommon misspellings) is
deliberately sequenced in a manner that propels the child's
development. The execution as described herein works off of a
ranked word learning model that analyzes the misspellings and uses
linguistic, orthographic, and morphologic characteristics of the
misspellings to generate a set of words bearing a similar word
structure to the misspellings, particularly the uncommon
misspellings, made by the child.
[0058] In the discussion that follows, small children are used as
exemplary users. However, it should be noted that embodiments of
the present invention are directed to users of various ages and/or
levels of development. Children move through varied and distinct
developmental stages as they acquire spelling skills. What begins
as an ability to recognize alphabets and their respective sounds,
develops into finding patterns within words and gradually
progresses to being able to string words together to form a
structurally and semantically coherent sentence. These different
stages that children experience in the process of learning and/or
writing words are often reflected by certain patterns that arise in
their spelling. Some embodiments of the present invention look to
certain unique patterns in spelling that are suggestive of the
child's progress in the process of internalizing language. In that
way, support is provided for spelling development and language
acquisition through chartered individualized plans built off
differentiated instruction.
[0059] There is a close association of work being performed with
cognitive computing pillars. The application of cognitive computing
in this description serves to emphasize the adaptive nature of that
platform and highlights the usefulness of a cognitive computing
service as a language acquisition buddy for children who tend to
have varied trajectories when it comes to acquiring proficiency in
language.
[0060] Some embodiments of the present invention learn the
misspellings made by a given child and perceive the cause of the
misspellings as opposed to merely recording the spelling as correct
or incorrect based solely on a rigid binary classification scheme,
such as one used in conventional spell checkers. The misspellings
made by a child are related to the misspellings made by other
children in a similar age group to infer the commonality of the
misspellings and to determines a trend in the misspellings by
differentiating the unique misspellings made by the child from the
common misspellings made by similarly situated children.
[0061] Some embodiments of the present invention adapt the language
training process according to a child's current stage in language
proficiency. For example, a new list of words is generated that not
only includes the misspellings the child has made, but also
includes words of similar orthographic structure to the
misspellings the child made in order to provide the child with
spelling instruction to specifically improve the language
development of the child.
[0062] Some embodiments of the present invention implement a
workflow step through a series of individual steps, with every
intermediate step focused at improving the functionality of a
"spelling buddy" for children who are yet to acquire proficiency in
language. The hypothesis is to tailor instruction suited to the
child's spelling competency through consistent positive
reinforcement with the child being motivated to make progress at
the child's own pace without any rigid expectations. Further, some
embodiments of the present invention provide relative assessments
by comparing the child's progress with the average progress of
other children of similar age-groups. Additionally, in some
embodiments, selected words are identified that the child
demonstrates a tendency to misspell so that rewards are provided to
the child for improvements with the selected words. The described
methodology ties in closely with the four pillars of a cognitive
platform. The functionality of some embodiments of the present
invention may be broadly classified under two categories: (i)
learning and perceiving; and (ii) relating and reasoning.
[0063] The category of learning and perceiving is invoked by
flagging a misspelled word with respect to a target word and
gaining perspective on a pattern in the misspelling and/or a type
of error that presents itself when comparing a misspelled word with
a correctly spelled word, or target word. The category of relating
and reasoning is invoked by utilizing a principle that finds its
origin in a reverse look up to intuitively ascertain why the word
that has been typed in is incorrect, differentiating between
spelling patterns that a child can and cannot recognize by aligning
the average child's progress in spelling development to the
individual caliber of the child, and using the insight gained
during the process to build a word knowledge base that augments
spelling, word recognition, vocabulary, phonics, and reading skills
in children.
[0064] FIG. 4 shows process flow 400 for analyzing misspellings
according to some embodiments of the present invention. Process 400
takes into account misspellings obtained from various sources
including: misspellings from websites 410; misspellings from data
sources 420; and misspellings from transcribed audio files 430,
such as the corpus developed by LumiDaOn. (Note: the term(s)
"LumiDaOn" may be subject to trademark rights in various
jurisdictions throughout the world and are used here only in
reference to the products or services properly denominated by the
marks to the extent that such trademark rights may exist.)
Transcribed audio files are used to identify common variations in
misspellings based on the approach that children tend to spell
words through letter-sound correspondences, so their manner of
saying a word would tend to likely match the way that the word is
spelled. These misspellings are used to generate a set of the top
five misspellings of certain words 440. Further, the misspellings
considered in process 400 are used to predict individualized
misspellings 450 according to, for example, similar types of
misspelling error(s).
[0065] Some embodiments of the present invention improve both
reading and writing skills of children and use the implicit
relationship between each of these skill sets to provide a
differentiated language instruction that is adapted to every
child.
[0066] Some embodiments of the present invention ensure that the
instruction provided is individualized, the model biases itself to
the misspellings a child continues to make to increase the
probability of displaying not only the misspelled word, but also
other words that belong in the same cluster as the misspelled word.
Accordingly, the child not only gains an understanding of the type
of misspellings that the child tends to make, but is also exposed
to other words that bear similar word structure to word that the
child tends to misspell.
[0067] Some embodiments of the present invention generate a set of
probabilistic percentages for common misspellings of a given word.
For example, the set of probabilistic percentages for misspelling
the word "obvious" may be as follows:
TABLE-US-00002 TABLE 1 Analysis of misspellings of the word
"obvious." MISSPELLING OF PERCENTAGE OF "OBVIOUS" MISSPELLINGS
OBVIUS 60 OBVIUZ 16 OBVIUOS 12 OBVIOAS 6 OBEOUS 6
[0068] Some embodiments of the present invention build word
knowledge bases by grouping words of similar orthographic structure
as a keyword. In FIG. 5, word knowledge base 500 is shown based on
the keyword "sitting" 502. The word knowledge base includes certain
orthographic structure groups associated with the keyword. In this
example, the orthographic structure groups are length 504a,
structure 504b, context 504c, and syllables 504d. Alternative
groupings are used according to various embodiments of the present
invention. In this example, a set of words is shown in knowledge
base 500, including: sorting, hitting, setting, standing, bending,
and running. According to some embodiments of the present
invention, orthographic features include: (i) spelling; (ii)
hyphenation; (iii) capitalization; (iv) word breaks; (v) emphasis;
and/or (vi) punctuation. The words illustrated in FIG. 5 are
similar for various and multiple structure groups. For example, the
word "standing" has more letters (length) than the target word, but
in contextually opposite of the target word (context), while it has
a similar structure in that it ends in the letters "ing"
(structure). Among the other words shown, the words "hitting" and
"setting" each have double t's in the spelling (structure), similar
to the target word, "sitting." Each word shown has the same number
of syllables as the target word.
[0069] Some embodiments of the present invention use standardized,
well-established rules to ascertain the nature of a misspelling
error by aligning the misspelled characters in the words to the
letters in the correctly spelled target word. Some embodiments of
the present invention rely on implicit learning as they work with a
vocabulary engine to generate other words bearing similar word
structure to the words that are misspelled. In that way, the
language instruction is tailored to work in accordance with the
stage at which the child, or other user, is at when acquiring
language proficiency. In some embodiments of the present invention,
a medical practitioner is contacted where a feature of misspellings
is determined to be representative of dyslexia/dysgraphia.
[0070] Some embodiments of the present invention identify factors
associated with spelling errors to identify types of errors and
perform automatically an action based on the type of error
detected. The action includes monitoring a plurality of users
entering text into a system for spelling errors, classifying
spelling errors according to rules to associate patterns of errors
with types of error, and, responsive to detecting a type of error
and characteristics of a user, constructing an augmented word
knowledge and utilizing the augmented word knowledge base to
perform automatically an action based on the type of error and the
characteristics of the user wherein the action is at least one of
educational (instructional), predictive (informational), and
corrective (identifying correctly spelled words). In some
embodiments, the characteristics of the user are selected from a
group consisting of demography, age, language exposure, and
education. In some embodiments, the root cause of a spelling error
is selected from a group consisting of dyslexia, dysgraphia, rote
visual memory, semi-phonetic, word morphology, typography, language
skill, literacy, and homonym.
[0071] Some embodiments of the present invention may include one,
or more, of the following features, characteristics and/or
advantages: (i) identification of misspelled words; (ii) provision
of corrective recommendations; (iii) analysis of these misspellings
to derive common error patterns; (iv) establishment of the
significance of grammatical errors to rote visual memory; (v)
establishment of the significance of grammatical errors to
semi-phonetic representations; (vi) establishment of the
significance of grammatical errors to word morphology; (vii)
understanding the misspellings users, such as children, make as
they discover the intricacies of English orthographic system;
(viii) usage of historic misspellings of a user as a future
spelling instruction guide to provide differentiated instruction as
the user acquires language as a skill; (ix) boosting language
acquisition rates; (x) provision of a spelling solution through a
language model that uses a graded relevance for spelling
correction; (xi) intelligent determination of the word sets to be
given to users as part of a thoughtful spelling improvement
strategy; (xii) generation of a new word list in accordance with
the user's prior mispronunciations; and/or (xiii) generation of a
new word list in accordance with the user's prior misspellings.
[0072] Some embodiments of the present invention may include one,
or more, of the following features, characteristics and/or
advantages: (i) provision of tailored instruction are provided
according to the user's weakness(es) in language comprehension;
(ii) drawing a correlation between the user's writing and reading
skills; (iii) alignment of the misspelled characters with the
corresponding letters in a correctly spelled target word; (iv)
identification of the cause of a misspelling event by tracking the
type of error; (v) recognition of a trend in the misspelling events
based on multiple writing samples of the same user; (vi)
identification of the cause of the misspelling as opposed to just
highlighting it; (vii) identification of whether a given child has
a tendency to delete characters from words; (viii) identification
of whether a child has a tendency to swap consecutive vowels when
spelling a word; (ix) every child is provided with spelling
instruction that matches their caliber at comprehending
letter-sound correspondences, syllable patterns, and/or morpheme
patterns; (x) distinguishing between generalizations and exceptions
in English language; and/or (xi) entirely automated as to
deciphering the causality of misspellings and associated intrinsic
trends in misspellings.
[0073] Some helpful definitions follow:
[0074] Present invention: should not be taken as an absolute
indication that the subject matter described by the term "present
invention" is covered by either the claims as they are filed, or by
the claims that may eventually issue after patent prosecution;
while the term "present invention" is used to help the reader to
get a general feel for which disclosures herein that are believed
as maybe being new, this understanding, as indicated by use of the
term "present invention," is tentative and provisional and subject
to change over the course of patent prosecution as relevant
information is developed and as the claims are potentially
amended.
[0075] Embodiment: see definition of "present invention"
above--similar cautions apply to the term "embodiment."
[0076] and/or: inclusive or; for example, A, B "and/or" C means
that at least one of A or B or C is true and applicable.
[0077] User/subscriber: includes, but is not necessarily limited
to, the following: (i) a single individual human; (ii) an
artificial intelligence entity with sufficient intelligence to act
as a user or subscriber; and/or (iii) a group of related users or
subscribers.
[0078] Module/Sub-Module: any set of hardware, firmware and/or
software that operatively works to do some kind of function,
without regard to whether the module is: (i) in a single local
proximity; (ii) distributed over a wide area; (iii) in a single
proximity within a larger piece of software code; (iv) located
within a single piece of software code; (v) located in a single
storage device, memory or medium; (vi) mechanically connected;
(vii) electrically connected; and/or (viii) connected in data
communication.
[0079] Computer: any device with significant data processing and/or
machine readable instruction reading capabilities including, but
not limited to: desktop computers, mainframe computers, laptop
computers, field-programmable gate array (FPGA) based devices,
smart phones, personal digital assistants (PDAs), body-mounted or
inserted computers, embedded device style computers,
application-specific integrated circuit (ASIC) based devices.
* * * * *